Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ienne
    -0.18
    ãĤ±ãĥĥãĥĪ
    -0.17
    chine
    -0.17
    omes
    -0.16
    angers
    -0.16
    atomic
    -0.16
    گاÙĩ
    -0.15
    ness
    -0.15
    im
    -0.15
    dao
    -0.15
    POSITIVE LOGITS
    making
    0.19
    book
    0.19
     thumb
    0.18
    enstein
    0.18
    ender
    0.18
    enda
    0.17
     ApplicationException
    0.17
    evenodd
    0.17
    vere
    0.16
    ansom
    0.16
    Act Density 0.026%

    No Known Activations